> ## Documentation Index
> Fetch the complete documentation index at: /docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Best practices

> Write better requests, pick the right mode and keep monitors cheap.

## Requests

* **Put the time window in the query.** Event runs read it from your words:
  "since Sep 15", "in Q3 2026".
* **Say what each row is.** "Each deal: buyer, target, value, date" gives you
  the columns you need instead of the ones the agent guesses.
* **One kind of event per run.** "Layoffs at US banks" and "bank M\&A deals"
  are better as two runs than one.
* **Narrow company runs with `query`.** Without it you get every story about
  the companies, including routine ones.

## Modes

* Start with `fast` to check that the request finds the right kind of event,
  then rerun in `standard` or `max` for the list you will use.
* Ask for the rows you need: a run is charged per 50 rows delivered past the
  first 50.

## Monitors

* Make monitors from runs whose results you checked, with `keep_updated` or
  `from_run_id`, so every delivery has the same columns.
* Use weekly schedules for slow-moving topics: every scheduled run is
  charged. See [Credits and pricing](/docs/get-started/credits-and-pricing.md#agent).
* Follow a company list instead of typing companies into each monitor, so one
  change to the list updates every monitor that uses it.
* Fix wrongly resolved companies in the list: runs and monitors from it use the
  correction.

## Integration

* Follow runs with the [progress stream](/docs/agent/runs.md#follow-a-run-live) in
  user-facing apps, and poll `GET /runs/{run_id}` in background jobs.
* Send your own `list_id` when you create a list with
  `POST /companies/lists`, so retries do not create duplicates.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.